© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14159
    Prev
    Next
    INDEX
    Explanations

    outcome, effectiveness, performance, discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (Void
    -0.20
    åľ¨éĤ£éĩĮ
    -0.19
    chandle
    -0.18
    è¿Ļä¹Īåģļ
    -0.18
     PARTICULAR
    -0.18
    西åĮĹ
    -0.17
    表éĿ¢ä¸Ĭ
    -0.17
    èĢĮä¸į
    -0.17
    apult
    -0.17
    индивид
    -0.17
    POSITIVE LOGITS
    à¸Ĥà¸Ńà¸ĩ
    0.29
     of
    0.29
     của
    0.27
     ש׾
    0.21
    of
    0.21
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.21
    èıĬ
    0.20
    /or
    0.20
    ation
    0.20
    agg
    0.20
    Activations Density 0.242%

    No Known Activations